Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions

TL;DR

The paper discusses the DCASE 2021 Challenge Task 2, focusing on unsupervised anomalous sound detection under domain shift conditions, highlighting novel ensemble and inlier modeling approaches that improve detection in practical scenarios.

Contribution

It introduces an advanced unsupervised ASD task under domain shift, analyzes top-performing methods, and identifies key strategies like ensemble and inlier modeling approaches.

Findings

Ensemble approaches of OE and IM detectors are effective.

IM-based detection on features from machine-identification tasks performs well.

Multiple novel methods were developed by participating teams.

Abstract

We present the task description and discussion on the results of the DCASE 2021 Challenge Task 2. In 2020, we organized an unsupervised anomalous sound detection (ASD) task, identifying whether a given sound was normal or anomalous without anomalous training data. In 2021, we organized an advanced unsupervised ASD task under domain-shift conditions, which focuses on the inevitable problem of the practical use of ASD systems. The main challenge of this task is to detect unknown anomalous sounds where the acoustic characteristics of the training and testing samples are different, i.e., domain-shifted. This problem frequently occurs due to changes in seasons, manufactured products, and/or environmental noise. We received 75 submissions from 26 teams, and several novel approaches have been developed in this challenge. On the basis of the analysis of the evaluation results, we found that there are two types of remarkable approaches that TOP-5 winning teams adopted: 1) ensemble approaches of ``outlier exposure'' (OE)-based detectors and ``inlier modeling'' (IM)-based detectors and 2) approaches based on IM-based detection for features learned in a machine-identification task.